KR20210097500A - Apparatus for Monitoring Fire And System having the same - Google Patents

Abstract

The present invention relates to a fire detecting apparatus and a system including the same for immediately supporting on-site fire response and reducing false detection based on artificial intelligence. Provided is the fire detecting apparatus comprising: a photographing unit that photographs a monitoring space and/or a monitoring area in real time to generate image data; a fire detecting unit that detects a fire outbreak based on artificial intelligence analysis of the image data to generate fire detection data; a data processing unit that processes and/or converts the fire detection data to generate monitoring data including an image and/or metadata; and a communicating unit that transmits the monitoring data to a control server.

Description

A fire detection device and a fire detection system including the same {Apparatus for Monitoring Fire And System having the same}

The present invention relates to a fire detection device and a fire detection system including the same, and more particularly, to a fire detection device capable of supporting an immediate on-site fire response and reducing the false positive rate based on artificial intelligence, and a fire detection system including the same is about

In general, a fire detection sensor and CCTV are installed in a building requiring fire detection to detect a fire.

In the case of fire detection by CCTV, the fire can be recognized only when the user directly monitors the acquired image, and the fire cannot be recognized if the user is not in the seat or does not look at the screen even when the user is in the seat. In addition, in the case of a fire detection sensor, a sensor installed in a building directly detects smoke or temperature as fire information and transmits the information to a central server to detect fire.

However, in the conventional fire detection system of this type, a fire is often detected due to a malfunction of the fire sensor even when it is not a fire, and there is a problem in that an unnecessary firefighting dispatch occurs by transmitting the false detection to the central server.

Korea Registered Patent No. 10-1075063

The technical problem to be solved by the present invention is to provide a fire detection device capable of supporting an immediate on-site fire response and reducing the false positive rate based on artificial intelligence, and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device capable of supporting personal information protection and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device capable of reducing network usage and image storage space and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device capable of remotely monitoring the occurrence of a fire, such as a flame or smoke, which may be generated in the field using image monitoring, and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is to create an image of the fire area by linking the drawing information of the building and support the decision-making on whether or not a fire has occurred using the display means to improve the convenience of decision-making. It is to provide a fire detection device and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device and a fire detection system including the same, which can improve the accuracy of fire occurrence by reflecting environmental information on the inside and outside of the fire zone and correcting fire errors. will do

In addition, the technical problem to be solved by the present invention is to provide a fire detection device and a fire detection system including the same, which can predict the direction of fire spread and provide additional control support to reduce additional damage caused by fire spread.

In addition, the technical problem to be solved by the present invention is to additionally match and verify the sensor data as needed to prevent a judgment error that occurs when a fire is detected based on only image data, thereby increasing the accuracy of fire detection. It is to provide a fire detection device and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is a fire detection device capable of calculating an effective fire evacuation route and/or fire suppression route by classifying a fire occurrence zone and a fire spread zone by linking the drawing information of the building, and a fire detection device including the same To provide a fire detection system.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device capable of improving the prediction accuracy for fire spread by setting a fire diffusion zone based on fire grade, wind direction, and wind speed, and a fire detection system including the same will be.

In addition, the technical problem to be solved by the present invention is to provide a fire detection device capable of classifying occupants and providing differentiated information to occupants, and a fire detection system including the same.

In addition, the technical problem to be solved by the present invention is a fire detection device that can be provided to evacuees and/or suppressors by monitoring the evacuation route and fire spread in real time to establish a safe evacuation route and an effective suppression route, and including the same To provide a fire detection system.

The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those of ordinary skill in the art to which the present invention belongs from the description below. There will be.

In order to achieve the above technical task, a photographing unit for generating image data by photographing a monitoring space and/or a monitoring area in real time; a fire detection unit that detects the occurrence of a fire based on artificial intelligence analysis of the image data and generates fire detection data; a data processing unit that processes and/or converts the fire detection data to generate monitoring data including images and/or metadata; and a communication unit for transmitting the monitoring data to a control server.

In an embodiment of the present invention, the fire detection unit includes: an image acquisition unit for acquiring a video image from the video data and dividing the video image into a plurality of blocks; an image processing unit for detecting a flame region and/or a smoke region from the image image divided into the plurality of blocks; and calculating the area and/or number of the detected flame area and/or smoke area, and comparing the calculated area and/or number of the flame area and/or smoke area with a fire occurrence reference value, and as a result of the comparison, the fire It may include a detection result output unit for generating and outputting the detection data.

In an embodiment of the present invention, the communication unit transmits building information to the control server, and receives at least one of a fire evacuation route and a fire suppression route from the control server, and the fire detection device transmits the building information. transmits a warning broadcast and/or turns on a warning emergency light according to the fire evacuation route and/or the fire suppression route using the It may further include a route guide.

In order to achieve the above technical task, a fire detection device for detecting the occurrence of a fire based on artificial intelligence analysis of real-time image data for the monitoring space and/or monitoring area and outputting monitoring data as a detection result; and receiving the monitoring data, decrypting and/or decrypting the received monitoring data to confirm and control the video, and transmit it to the control terminal of the control person working in the field and/or control room to receive a pop-up notification and/or from the control terminal Or, it provides a fire detection system, including a control server for notifying the detection result to display the detection result by sound output.

In an embodiment of the present invention, the fire detection device includes: a photographing unit for generating image data by photographing a monitoring space and/or a monitoring area in real time; a fire detection unit that detects the occurrence of a fire based on artificial intelligence analysis of the image data and generates fire detection data; a data processing unit that processes and/or converts the fire detection data to generate monitoring data including images and/or metadata; and a communication unit for transmitting the monitoring data to a control server.

In an embodiment of the present invention, the fire detection unit includes: an image acquisition unit for acquiring a video image from the video data and dividing the video image into a plurality of blocks; an image processing unit for detecting a flame region and/or a smoke region from the image image divided into the plurality of blocks; and calculating the area and/or number of the detected flame area and/or smoke area, and comparing the calculated area and/or number of the flame area and/or smoke area with a fire occurrence reference value, and as a result of the comparison, the fire It may include a detection result output unit for generating and outputting the detection data.

In an embodiment of the present invention, the control support unit may include: a zone image generator configured to generate an image in a two-dimensional or three-dimensional zone by reflecting the information on the location where the fire sign is sensed and the drawing information of the building; a fire symptom correction unit for receiving environmental information of any one or more of illuminance, temperature, humidity, wind direction, and pongsok of the area through a weather information sensor installed inside and/or outside the building, and correcting the detected fire signs; and a fire spread information generating unit that calculates and additionally generates a surrounding area where fire is expected to spread within a set time through the area based on the fire sign and the environmental information.

In an embodiment of the present invention, the control supplementary unit includes: a sensor data collection unit for collecting sensor data through a sensor installed at a position corresponding to an area identified through the image data; an information matching unit that matches the occurrence/continuation of occurrence/continuation of abnormal temperature and/or humidity collected through the sensor data with the flame generation and/or smoke generation information confirmed through the image data; and a reading verification unit that reads whether a final fire has occurred as a result of the matching and performs a control supplementary function.

In an embodiment of the present invention, the route information providing unit includes: a fire zone setting unit for classifying a fire area and/or a fire spread area; a fire warning unit that transmits a warning broadcast and/or turns on a warning emergency lamp; and a fire notification unit that calculates a fire evacuation route and/or a fire suppression route, and selectively informs an evacuee and/or a suppressor of the fire escape route and/or fire suppression route.

In an embodiment of the present invention, the fire zone setting unit includes: a fire zone image generator for generating an image as a two-dimensional or three-dimensional zone by reflecting building information with information on a location corresponding to the fire zone; and within a time set through the fire zone based on the fire class and/or wind direction and/or pongsok information affecting the zone and the adjacent zone. It may include a fire spread area setting unit that calculates and additionally generates a fire spread area where fire is expected to spread, and divides the fire occurrence area and the fire spread area.

In an embodiment of the present invention, the fire notification unit may guide the fire evacuation route and/or fire suppression route by setting a display color and/or a blinking pattern of a pre-installed route display device.

In an embodiment of the present invention, the fire notification unit includes at least one fire evacuation route based on movement path information of the building structure including the fire occurrence zone, the fire spread zone, and the fire occurrence zone and the fire spread zone. an evacuation route generating unit to generate a suppression path generation unit for generating at least one fire suppression path based on information on a movement path of the fire generating area, the fire spreading area, and the building structure including the fire generating area and the fire spreading area; an occupant characteristic analysis unit for checking whether the occupants located inside the building structure are evacuees or suppressors; and a route recommendation unit for recommending an evacuation route when the occupant is an evacuee and a suppression route when the occupant is a suppressor.

In an embodiment of the present invention, the route information providing unit includes: an evacuation route monitoring unit for monitoring the evacuation status of evacuees on the set evacuation route; an evacuation risk monitoring unit that checks in real time whether the evacuation route and the fire spread area overlap each other according to the real-time and/or set time spread prediction information; and an evacuation route resetting unit configured to reset the evacuation route when it is expected that the evacuation route and the fire spread area overlap.

According to an embodiment of the present invention, it is possible to support an immediate on-site fire response and reduce the false positive rate based on artificial intelligence of deep learning.

In addition, according to an embodiment of the present invention, it is possible to support personal information protection through personal information masking, compression, and encryption.

In addition, according to an embodiment of the present invention, network usage and image storage space can be reduced through image and/or metadata transmission.

In addition, the present invention can reduce the cost of the image analysis server through on-site installation of the fire detection device.

In addition, according to the embodiment of the present invention, it is possible to minimize the infrastructure change of the control server.

In addition, according to an embodiment of the present invention, it is possible to remotely monitor the occurrence of a fire, such as a flame or smoke, which may be generated in the field using image monitoring.

In addition, according to an embodiment of the present invention, it is possible to improve the convenience of decision-making by generating an image of a fire-occurring area using building information and supporting decision-making as to whether or not a fire has occurred using the display means.

In addition, according to an embodiment of the present invention, the accuracy of fire occurrence can be improved by correcting a fire error by reflecting the environmental information on the inside and outside of the fire zone in connection.

In addition, according to an embodiment of the present invention, it is possible to predict the direction of fire spread and provide additional control support to reduce additional damage caused by fire spread.

In addition, according to an embodiment of the present invention, in order to prevent a judgment error that occurs when a fire is detected based on only image data, the sensor data is additionally matched and verified as needed, thereby increasing the accuracy of fire detection. .

In addition, according to an embodiment of the present invention, an effective fire evacuation route and/or fire suppression route can be calculated by classifying a fire occurrence zone and a fire spread zone using building information.

In addition, according to an embodiment of the present invention, it is possible to improve the prediction accuracy of the fire spread by setting the fire spread area based on the fire grade, wind direction, and wind speed.

Also, according to an embodiment of the present invention, differentiated information can be provided to occupants by classifying occupants.

In addition, according to an embodiment of the present invention, it is possible to set a safe evacuation route and an effective suppression route by monitoring the evacuation route and fire spread in real time, and provide it to evacuees and/or suppressors.

It should be understood that the effects of the present invention are not limited to the above-described effects, and include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a diagram showing the configuration of a fire detection system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a network connection of the control server of FIG. 1 .
FIG. 3 is a view showing in detail the configuration of the fire detection device of FIG. 1 .
FIG. 4 is a view showing in detail the configuration of the fire detection unit of FIG. 3 .
FIG. 5 is a diagram showing the configuration of the control server of FIG. 1 in detail.
FIG. 6 is a view showing in detail the configuration of the control support unit of FIG. 5 .
7 is a view showing in detail the configuration of the control supplementary unit of FIG.
FIG. 8 is a view showing in detail the configuration of the route information providing unit of FIG. 4 .
9 is a view showing in detail the configuration of the fire zone setting unit of FIG.
FIG. 10 is a diagram illustrating in detail the configuration of the route notification unit of FIG. 8 .

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be embodied in several different forms, and thus is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be “connected (connected, contacted, coupled)” with another part, it is not only “directly connected” but also “indirectly connected” with another member interposed therebetween. "Including cases where In addition, when a part "includes" a certain component, this means that other components may be further provided without excluding other components unless otherwise stated.

The terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprises" or "have" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram showing the configuration of a fire detection system according to an embodiment of the present invention.

FIG. 2 is a diagram illustrating a network connection of the control server of FIG. 1 .

1 and 2 , a fire detection system according to an embodiment of the present invention may include a fire detection device 100 and a control server 200 .

The fire detection device 100 may detect the occurrence of a fire based on artificial intelligence analysis of real-time image data for a monitoring space and/or a monitoring area, and output monitoring data as a detection result. To this end, referring to FIG. 3 , the fire detection device 100 may include a photographing unit 110 , a fire detection unit 120 , a data processing unit 130 , a communication unit 140 , and a route guide unit 150 . can

The photographing unit 110 may generate image data by photographing a monitoring space and/or a monitoring area set in a building, a factory, etc. in real time. To this end, the photographing unit 110 may photograph with a camera-based video monitoring device (including CCTV, etc.).

The fire detection unit 120 may generate fire detection data by detecting the occurrence of a fire based on artificial intelligence analysis of the image data. To this end, referring to FIG. 4 , the fire detection unit 120 acquires an image image from the image data, and an image acquisition unit 122 that divides the image image into a plurality of blocks, each of the plurality of blocks. The image processing unit 124 for detecting the flame area and/or smoke area from the divided image image and the area and/or number of the detected flame area and/or smoke area are calculated, but the calculated flame area and/or smoke area The detection result output unit 126 may include a detection result output unit 126 that compares the area and/or the number of regions with a fire occurrence reference value, and generates and outputs fire detection data as a result of the comparison.

The image acquisition unit 122 may receive an image from the photographing unit 110 , and may generate an image image corresponding to a still screen from the received image. Also, the image acquisition unit 122 may divide the video image into a plurality of preset blocks. In this case, the image acquisition unit 122 may generate a plurality of blocks by dividing the video image into a preset number and/or size.

The image processing unit 124 may detect a flame region and/or a smoke region from the image image according to a set method. In addition, the image processing unit 124 may detect a flame region and/or a smoke region from the image image using deep learning-based, for example, Edge IoT-based artificial intelligence analysis.

First, the flame region detection method of the image processing unit 124 is described. The image processing unit 124 utilizes YCbCr (sampling frequency ratio of luminance signal and chrominance signal) (Y: luminance, CbCr: color) to obtain an image image. It is possible to detect the flame area from In more detail, the image processing unit 124 may convert the video image into a preset YCbCr (sampling frequency ratio of a luminance signal and a chrominance signal) (Y: luminance, CbCr: color) color space. Also, the image processing unit 124 may remove the harmful effect of generating illuminance in the YCbCr color space with reference to Equation 1 below.

[Equation 1]

In addition, the image processing unit 124 may define a point of (x, y) satisfying 1 in Equation 1 as a flame pixel.

[Equation 2]

In Equation 2, τ is a constant and may be determined by ROC (Receiver Operating Characteristics) analysis. Here, ROC is a graph of probability of hit versus probability of false alarm in signal detection theory. there is. On the other hand, the upper right is a case of saying “Yes” unconditionally, and the upper left may mean making a perfect distinction. That is, the ROC graph may be more conservative toward the lower left and more adventurous toward the upper right.

In addition, the image processing unit 124 may determine the flame region from the flame candidate region by image processing the flame candidate region after separating the flame candidate region from the image image. Here, the image processing unit 124 determines the flame area by analyzing the flame candidate area according to the flame determination standard, and the flame determination standard is the irregularity observed on the flame surface, the roughness of the flame, the amount of change in the flame area, and 3 of the fire area. It may be set including at least one of the difference probability moments. In this case, the third probability moment can be obtained with reference to Equation 3 below.

[Equation 3]

Next, the method of detecting a smoke region of the image processing unit 124 will be described. The image processing unit 124 may detect a smoke candidate region from the image image by applying a random forest classification technique to the image image. Here, the smoke has a characteristic of rising in the atmosphere because it is very light because the particle size is 0.1 ~ 1 μm, and it is white, gray, and black, and it is desirable to detect it using the three characteristics of brightness, motion accumulation, and diffusion. In addition, since outdoor smoke is greatly affected by external environmental variables, it is desirable to apply a random forest classification technique.

In more detail, the image processing unit 124 may compare consecutively captured image images and set a block of the smoke candidate region equal to or greater than the detection reference value as the region of interest. Also, the image processing unit 124 may learn different random forests for a plurality of regions of interest, and may generate a cumulative probability histogram by accumulating classes generated as a result of the learning. Also, the image processing unit 124 may determine the smoke area from the generated histogram. Through this, the image processing unit 124 may detect the outside of the diffused smoke.

In addition, the random forest is an ensemble method for learning a plurality of decision trees, and uses a classification and regression tree (CART) such as a method that combines randomized node optimization and bootstrap aggregating bagging without correlation. How to construct a forest with trees. Such a random forest may have characteristics such as high accuracy, a simple and fast learning and testing algorithm, and generalization through randomization.

The detection result output unit 126 calculates the block area and/or the number of blocks of the detected flame area and/or smoke area, and calculates the calculated block area and/or the number of blocks in the flame area and/or smoke area to generate a fire. After comparison with the reference value, if the block area and/or the number of blocks is greater than the fire occurrence reference value, fire detection data may be generated as a fire detection result. Also, the detection result output unit 126 may output the fire detection data to the data processing unit 130 .

The data processing unit 130 may process and/or convert the fire detection data to generate monitoring data including images and/or metadata.

Specifically, the data processing unit 130 may detect personal information from the monitoring data for personal information protection, and process the monitoring data by applying object masking and/or scrambling to the personal information. In addition, the data processing unit 130 may support the compression of the monitoring data in order to reduce the capacity of the image (fire image) of the monitoring data. In addition, the data processing unit 130 may support transmission encryption using metadata of the monitoring data for information protection.

The communication unit 140 may transmit the monitoring data to the control server 200 which is an external device. In addition, the communication unit 140 may transmit the fire detection device 100 and/or self-stored building information to the control server 200 . Also, the communication unit 140 may receive at least one of a fire evacuation route and a fire suppression route from the control server 200 . Here, the building information includes at least one of building types classified into office buildings, factories, etc., drawing (map) information of monitoring spaces and/or monitoring areas, interior information about interior and/or exterior, and number of occupants by time. can

The route guide unit 150 transmits a warning broadcast and/or turns on a warning emergency light according to the fire evacuation route and/or the fire suppression route using the building information, and the fire evacuation route and/or fire suppression route may optionally be notified to evacuees and/or oppressors.

On the other hand, the fire detection device 100 detects fire (1 time / 10 seconds), temperature / carbon dioxide change detection (10 seconds), operation check (1 time / second), temperature / carbon dioxide increase continuous detection for more than 1 minute ( 1 time/min) and so on. To this end, the fire detection device 100 may further include a sensor capable of detecting temperature and/or gas (gas), and a control device operating a set operation according to the cycle setting.

For example, the fire detection device 100 may transmit the building information and the monitoring data including an image to the control server 200 through the communication unit 140 at set time intervals.

The control server 200 receives the monitoring data when a fire is detected in the fire detection device 100, decrypts and/or decrypts the received monitoring data to confirm and control the image, and display the on-site and / Or, it is possible to notify the detection result so that the detection result is displayed as a pop-up notification and/or sound output from the control terminal by sending it to the control terminal of the control person in charge working in the control room. To this end, the control server 200 may include a control support unit 300 , a control supplementary unit 310 , a remote control supplementary unit 400 , a fire notification unit 500 , and a route information providing unit 600 . .

The control support unit 300, when a fire is detected in the fire detection device 100, transmits the detection result of the fire to the control terminal of the control person working at the site and/or the control room, and a pop-up notification from the control terminal and/or notifying the detection result to display the detection result by sound output. At this time, the control support unit 300 may support the control of fire occurrence so that the control person in charge can more effectively inform and warn the field after the final review of the fire occurrence area visualized through the pop-up window of the control terminal. That is, the control support unit 300 may support the control person to check whether a fire has occurred through the decision support system.

To this end, referring to FIG. 6 , the control support unit 300 generates a zone image generating unit 301 that generates information on a location where the fire is detected as a two-dimensional or three-dimensional zone by reflecting the drawing information of the building. ), receives environmental information of any one or more of illuminance, temperature, humidity, wind direction, and pongsok of the area through a weather information sensor installed inside and/or outside the building, and corrects the detected fire occurrence. 303 and a fire spread information generating unit 305 that additionally generates by calculating a surrounding area where fire is expected to spread within a set time through the area based on the occurrence of the fire and the environmental information.

When the fire detection unit 200 detects the occurrence of a fire, the control supplementary unit 310 may perform a control supplementary function to improve the accuracy of decision-making as to whether or not a fire has occurred. To this end, referring to FIG. 7 , the control supplementary unit 310 includes an image data collection unit 311 that collects image data for a monitoring space and/or a monitoring area, corresponding to the area identified through the image data. A sensor data collection unit 313 that collects sensor data through a sensor installed at a location, spark generation and/or smoke generation information confirmed through the image data, and abnormal temperature and/or humidity generated through the sensor data It may include an information matching unit 315 for matching / continuity and a reading verification unit 317 for performing a control supplement function by reading whether a final fire has occurred as a result of the matching.

Here, the information matching unit 315 matches the image data on the flame generation with the first sensor data on the flame to read a first matching function for reading whether the flame is generated, and the image data on the smoke generation and the second sensor data on the smoke. At least one matching function of a second matching function of matching sensor data to read whether or not smoke is generated, and a third matching function of detecting an abnormal temperature by matching the image data for the abnormal temperature with the third sensor data for the temperature can be done

In the control supplementary unit 310, a sensor that detects at least one of flame, smoke, temperature and humidity as well as image data collected through an image monitoring device including CCTV to more accurately detect and read whether a fire has occurred. By using the sensor data collected through

The remote control supplementary unit 400 may support supplementary confirmation of whether a fire has occurred through remote support in situations where additional responses are required, such as when there is no response (response) within the time set in the field and/or control room. . If, in the field and/or control room, the decision as to whether or not a fire occurs for a set period of time according to the situation is not processed, the remote control supplement unit 400 determines whether a fire occurs by remote support in order to quickly cope with the fire. can assist in making decisions about

For example, the remote control supplementary unit 400 notifies a fire detection result to the control terminal and/or mobile terminal of a supervisor and/or a colleague of the control person in charge, and then makes a decision on whether or not a fire occurs with remote support. You can take input and process it. In addition, when the control person in charge is absent at the site and/or the control room, the remote control supplement unit 400 notifies the detection result of the fire occurrence not only to the control terminal but also to the portable terminal, and then makes a decision on whether or not a fire has occurred with remote support. can be input and processed.

The fire notification unit 500 may notify and/or warn of fire in the monitoring area and/or monitoring space where the occurrence of a fire is confirmed, and may support follow-up measures such as fire evacuation. For example, the fire notification unit 500 may transmit a fire notification broadcast using a speaker or turn on a fire notification light using a lighting device.

Referring to FIG. 8 , the route information providing unit 600 includes a fire zone setting unit 610 for classifying a fire occurrence zone and/or a fire spread zone, and a fire warning that transmits a warning broadcast and/or turns on a warning emergency lamp. Calculating the fire evacuation route and/or fire suppression route, and calculating the fire evacuation route and/or fire suppression route, the route notification part 630 may include a unit 620 and a route notification unit 630 to selectively inform evacuees and/or suppressors of the fire evacuation route and/or fire suppression route. there is.

Referring to FIG. 9 , the fire zone setting unit 610 generates a fire zone image that generates an image in a two-dimensional or three-dimensional zone by reflecting information on the location of the fire zone corresponding to the building's drawing information. Based on the section 611 and the fire class of the fire-occurring area and the area located in the vicinity of the fire-occurring area, and/or the wind direction and/or pongsok information affecting the area and the adjacent area, the fire-occurring area is determined. It may include a fire spread area setting unit 613 that calculates and additionally generates a fire spread area in which the fire is expected to spread within a set time, and divides the fire occurrence area and the fire spread area.

The fire warning unit 620 may transmit a broadcast signal to output a warning broadcast using a speaker, or may transmit a lighting signal to turn on a warning emergency lamp using a warning display device.

The route notification unit 630 may provide visualized information to evacuees and suppressors about the fire evacuation route and fire suppression route of the group when a fire occurs. To this end, referring to FIG. 10 , the route notification unit 630 is based on information on the movement path of the building including the fire occurrence area information (image), the fire spread area information (image), the fire occurrence area and the fire spread area. evacuation route generating unit 631 that generates at least one fire evacuation route with A suppression path generation unit 633 that generates at least one fire suppression path based on It may include a route recommendation unit 637 that recommends an evacuation route if the occupant is a suppressor or recommends a suppression route if the occupant is a suppressor.

The route notification unit 630 may guide a fire evacuation route and/or a fire suppression route by setting a display color and/or a blinking pattern of a pre-installed route display device.

On the other hand, the route information providing unit 600, the evacuation route monitoring unit 650 for monitoring the evacuation status of the evacuees on the set evacuation route, real-time and / or set time of the evacuation route and the fire spread area of the evacuation route An evacuation risk monitoring unit 660 that checks in real time whether there is overlap according to the internal spread prediction information, and an evacuation route resetting unit 670 that resets the evacuation route when the overlap between the evacuation route and the fire spread area is expected. can do.

On the other hand, the control server 200 that receives the monitoring data at a set time interval from the fire detection device 100 checks the signal state connectivity through a normal signal, and when the fire detection device 100 detects a fire Information can be received as the time increases from every minute to 10 seconds. If this state continues for more than 1 minute, the control server 100 may warn (notify) the control person in charge. In addition, the control person can check the image status of the monitoring data transmitted for 1 minute as soon as the warning (notification) is received, and notify the fire occurrence to the manager and/or suppressor of the building through the control server 200 .

As described above, the present invention can support an immediate on-site fire response and reduce the false positive rate based on artificial intelligence of deep learning.

In addition, the present invention can support personal information protection through personal information masking, compression, and encryption.

In addition, the present invention can reduce network usage and image storage space through image and/or metadata transmission.

In addition, the present invention can reduce the cost of the image analysis server through on-site installation of the fire detection device.

In addition, the present invention can minimize the infrastructure change of the control server.

In addition, the present invention can remotely monitor the occurrence of a fire such as a flame or smoke that may be generated in the field using image monitoring.

In addition, the present invention can improve the convenience of decision-making by creating an image of a fire area by linking the drawing information of the building and supporting the decision-making as to whether or not a fire has occurred by using the display means.

In addition, the present invention can improve the accuracy of fire occurrence by correcting a fire error by reflecting the environmental information on the inside and outside of the fire zone in connection.

In addition, the present invention can reduce the additional damage caused by the fire spread by predicting the direction of fire spread and supporting additional control.

In addition, according to the present invention, in order to prevent a judgment error occurring when a fire is detected based on only image data, the sensor data is additionally matched and verified as needed, thereby increasing the accuracy of fire detection.

In addition, the present invention can calculate an effective fire evacuation route and/or fire suppression route by classifying a fire occurrence zone and a fire spread zone using building information.

In addition, the present invention can improve the prediction accuracy of the fire spread by setting the fire spread area based on the fire grade, wind direction, and wind speed.

In addition, the present invention can provide differentiated information to occupants by classifying occupants.

In addition, the present invention can monitor the evacuation route and fire spread in real time to set a safe evacuation route and an effective suppression route, and provide it to evacuees and/or suppressors.

The description of the present invention described above is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention.

100: fire detection device
110: shooting department
120: fire detection unit
130: data processing unit
140: communication department
150: route guide
200: control server
300: control support department
310: control and supplement department
400: remote control supplementary department
500: fire notification department
600: route information providing unit

Claims (15)

a photographing unit generating image data by photographing the monitoring space and/or the monitoring area in real time;
a fire detection unit that detects the occurrence of a fire based on artificial intelligence analysis of the image data and generates fire detection data;
a data processing unit that processes and/or converts the fire detection data to generate monitoring data including images and/or metadata; and
a communication unit for transmitting the monitoring data to a control server;
Including, a fire detection device.
According to claim 1,
The fire detection unit,
an image acquisition unit that acquires a video image from the video data and divides the video image into a plurality of blocks;
an image processing unit for detecting a flame region and/or a smoke region from the image image divided into the plurality of blocks; and
Calculating the area and/or number of the detected flame area and/or smoke area, comparing the calculated area and/or number of the flame area and/or smoke area with a fire occurrence reference value, and detecting the fire as a result of the comparison a detection result output unit for generating and outputting data;
A fire detection device comprising a.
According to claim 1,
The communication unit,
Sending building information to the control server, and receiving at least one of a fire evacuation route and a fire suppression route from the control server,
The fire detection device is
By using the building information, a warning broadcast is transmitted and/or a warning emergency light is turned on according to the fire evacuation route and/or the fire suppression route, and the fire evacuation route and/or the fire suppression route are used for evacuation and/or suppression. Fire detection device, characterized in that it further comprises a route guide to selectively inform the.
a fire detection device that detects a fire occurrence based on artificial intelligence analysis of real-time image data for a monitoring space and/or a monitoring area and outputs monitoring data as a detection result; and
Receives the monitoring data, decrypts and/or decrypts the received monitoring data to confirm and control the video, and transmits it to the control terminal of the control person working in the field and/or control room to receive a pop-up notification and/or a control server that notifies the detection result to display the detection result with sound output;
Including, a fire detection system.
5. The method of claim 4,
The fire detection device is
a photographing unit generating image data by photographing the monitoring space and/or the monitoring area in real time;
a fire detection unit that detects the occurrence of a fire based on artificial intelligence analysis of the image data and generates fire detection data;
a data processing unit that processes and/or converts the fire detection data to generate monitoring data including images and/or metadata; and
a communication unit for transmitting the monitoring data to a control server;
Including, a fire detection system.
6. The method of claim 5,
The fire detection unit,
an image acquisition unit that acquires a video image from the video data and divides the video image into a plurality of blocks;
an image processing unit for detecting a flame region and/or a smoke region from the image image divided into the plurality of blocks; and
Calculating the area and/or number of the detected flame area and/or smoke area, comparing the calculated area and/or number of the flame area and/or smoke area with a fire occurrence reference value, and detecting the fire as a result of the comparison a detection result output unit for generating and outputting data;
A fire detection system comprising a.
6. The method of claim 5,
The communication unit,
Sending building information to the control server, and receiving at least one of a fire evacuation route and a fire suppression route from the control server,
The fire detection device is
By using the building information, a warning broadcast is transmitted and/or a warning emergency light is turned on according to the fire evacuation route and/or the fire suppression route, and the fire evacuation route and/or the fire suppression route are used for evacuation and/or suppression. Fire detection system, characterized in that it further comprises a route guide to selectively inform the.
5. The method of claim 4,
The control server is
a control support unit that supports decision-making on whether or not a fire has occurred by using an indication means to the control person in charge;
a control supplementary unit supporting a control supplementary function to improve the accuracy of the decision-making;
a remote control supplementary unit that supplements decision-making on whether or not a fire occurs with remote support in a situation where there is no response from the control person within the set time;
a fire notification unit that notifies and warns of a fire in the monitoring space and/or monitoring area where the occurrence of a fire is confirmed; and
a route information providing unit for providing information set to evacuees and suppressors on an optimal fire preparedness route and fire suppression route;
A fire detection system comprising a.
9. The method of claim 8,
The control support department,
a zone image generator for generating an image in a two-dimensional or three-dimensional zone by reflecting the information on the location where the fire sign is detected;
a fire sign correction unit for receiving environmental information of any one or more of illuminance, temperature, humidity, wind direction, and pongsok of the area through a weather information sensor installed inside and/or outside the building, and correcting the detected fire signs; and
a fire spread information generating unit that calculates and additionally generates a surrounding area where fire is expected to spread within a set time through the area based on the fire sign and the environmental information;
A fire detection system comprising a.
9. The method of claim 8,
The control supplementary unit,
a sensor data collection unit configured to collect sensor data through a sensor installed at a location corresponding to an area identified through the image data;
an information matching unit for matching whether or not the occurrence/continuation of abnormal temperature and/or abnormal humidity collected through the sensor data with the flame generation and/or smoke generation information confirmed through the image data; and
a reading verification unit that reads whether a final fire has occurred as a result of the matching and performs a control supplementary function;
A fire detection system comprising a.
9. The method of claim 8,
The route information providing unit,
a fire zone setting unit for classifying a fire area and/or a fire spread area;
a fire warning unit that transmits a warning broadcast and/or turns on a warning emergency lamp; and
a fire notification unit that calculates a fire evacuation route and/or a fire suppression route, and selectively notifies the fire escape route and/or fire suppression route to evacuees and/or suppressors;
A fire detection system comprising a.
12. The method of claim 11,
The fire zone setting unit,
a fire-occurring area image generation unit for generating an image as a two-dimensional or three-dimensional area by reflecting the information on the location corresponding to the fire area to the drawing information of the building; and
Fire within the time set through the fire zone based on the fire class and/or wind direction and/or pongsok information affecting the zone and the zone adjacent to the zone a fire spread area setting unit that calculates and additionally generates a fire spread area where the spread is expected and divides the fire area from the fire spread area;
comprising, a fire detection system.
12. The method of claim 11,
The fire alarm unit,
A fire detection system, characterized in that by setting the display color and/or blinking pattern of a pre-installed path display device to guide the fire evacuation path and/or fire suppression path.
12. The method of claim 11,
The fire alarm unit,
an evacuation route generator configured to generate at least one fire evacuation route based on the fire occurrence zone, the fire spread zone, and movement route information of a building structure including the fire occurrence zone and the fire spread zone;
a suppression path generation unit for generating at least one fire suppression path based on information on a movement path of the fire generating area, the fire spreading area, and the building structure including the fire generating area and the fire spreading area;
an occupant characteristic analysis unit for checking whether the occupants located inside the building structure are evacuees or suppressors; and
a route recommendation unit for recommending an evacuation route when the occupant is an evacuee, and a suppression route when the occupant is a suppressor;
A fire detection system comprising a.
12. The method of claim 11,
The route information providing unit,
an evacuation route monitoring unit for monitoring the evacuation status of evacuees on the set evacuation route;
an evacuation risk monitoring unit for checking in real time whether the evacuation route and the fire spread area overlap each other according to the real-time and/or set time spread prediction information; and
an evacuation route resetting unit for resetting the evacuation route when the evacuation route and the fire spread area overlap are expected;
Further comprising a, fire detection system.

Images